Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 4170
    Prev
    Next
    INDEX
    Explanations

    discussions related to financial systems and their comparative efficiency, particularly concerning social security and health insurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iese
    -0.16
    UGIN
    -0.15
    виÑī
    -0.15
    ायन
    -0.15
    riott
    -0.14
    å±Ģ
    -0.14
     вÑĩ
    -0.14
    stroy
    -0.14
     dic
    -0.14
    ORIA
    -0.14
    POSITIVE LOGITS
     peer
    0.18
     envy
    0.18
     rankings
    0.18
     OECD
    0.17
     levels
    0.17
     developed
    0.17
     relative
    0.17
     ranking
    0.16
     Organisation
    0.16
     advanced
    0.16
    Activations Density 0.099%

    No Known Activations